This paper describes the participation of the the MRIM research Group of the LIG laboratory in the ImageCLEF scalable concept image annotation subtask 1. We made use of a classical framework to annotate the 500K images of this task: we tuned an existing Convolutional Neural Network model to learn the 251 concepts and to locate bounding boxes of such concepts, and we applied a specific process t...

We conducted a protocol study of the architectural sketching process. We decompose the process into process flows to explore the extent to which it expresses concept development in schematic and refined design phases. We track the development of design concepts in these phases by following the process flows of individual sketched strokes. We argue that each stroke drawn by the designer reveals ...

Large data resources are ubiquitous in science and business. For these domains, an intuitive view on the data is essential to fully exploit the hidden knowledge. Often, these data can be semantically structured by concepts. Since the determination of concepts requires a thorough analysis of the data, data mining methods have to be applied. In the field of subspace clustering, some techniques ha...

Fuzzy Formal Concept Analysis (FCA) is a mathematical tool for the effective representation of imprecise and vague knowledge. However, with a large number of formal concepts from a fuzzy context, the task of knowledge representation becomes complex. Hence, knowledge reduction is an important issue in FCA with a fuzzy setting. The purpose of this current study is to address this issue by proposi...

It seems self-evident that the way to teach mathematics is to start from simple concepts familiar to the learner and to build more complex ideas through a sequence of activities growing steadily in sophistication. It is a salutary experience to learn that a curriculum carefully built in this way can cause serious difficulties in learning. The problem arises because the human mind does not opera...

Theme-based learning (TBL) refers to learning modes which adopt the following sequence: (a) finding the theme; (b) finding a focus of interest based on the theme; (c) finding materials based on the focus of interest; (d) integrating the materials to establish shared knowledge; (e) publishing and sharing the integrated knowledge. We have created an on-line system which supports the TBL mode to p...

This paper describes UAIC’s system built for participating in the Scalable Concept Image Annotation challenge 2016. We submitted runs for Subtask 1 (Image annotation and localisation), for Subtask 2 (Natural language caption generation) and for Subtask 3 (Content Selection). For the first subtask we used an ontology created last year with relations between concepts and their synonyms, hyponyms ...

In this article we report on the experiments conducted by the IPL team within the context of the ImageCLEF 2014 challenge on Scalable Concept Image Annotation. Our approach encompasses, a CBIR phase following with a concept extraction procedure. The content based retrieval utilizes Latent Semantic Analysis on a set of multiple Compact Composite Features to retrieve the most similar images and i...

In this paper we describe our image annotation system participated in the ImageCLEF 2014 scalable concept image annotation task. The system is fully SVM based. Per concept we learn an ensemble of fast intersection kernel SVMs from three sources of training data, all obtained with manual annotation for free. The focus of our experiments this year is to answer the question of how many tags we sho...

This paper presents an overview of the ImageCLEF 2014 evaluation lab. Since its first edition in 2003, ImageCLEF has become one of the key initiatives promoting the benchmark evaluation of algorithms for the annotation and retrieval of images in various domains, such as public and personal images, to data acquired by mobile robot platforms and medical archives. Over the years, by providing new ...